[DEVELOPMENT] Consider splitting all classifier options into individual torch.nn.Module
objects
#279
Labels
methodology
Building functional & diverse pipeline
The current implementation uses a single
GNNModel
and based on theclassifier_type
&hidden_channels
arguments builds an appropriate model. Consider breaking this down into separate objects forLinearModel
,GCNModel
,GATModel
, etc.Potential drawback: load of code duplication, esp. in self.forward() and when calling the model for prediction.
The text was updated successfully, but these errors were encountered: